INDEX

Explanations

references to the letter 'X' and its associations, particularly in scientific or technical contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yakarta

-0.60

 honn

-0.47

yszcz

-0.47

 most

-0.47

"=>"

-0.46

use

-0.45

@",

-0.45

تماد

-0.43

ibouti

-0.43

PhysRevLett

-0.43

POSITIVE LOGITS

2.22

2.01

 getX

1.42

Xs

1.41

getX

1.39

setX

1.26

×

1.13

Xo

1.09

Ｘ

1.08

Activations Density 0.245%

references to the letter 'X' and its associations, particularly in scientific or technical contexts

No Comments

No Known Activations